{"id":"https://openalex.org/W7160592995","doi":"https://doi.org/10.48550/arxiv.2605.06289","title":"Multimodal Deep Generative Model for Semi-Supervised Learning under Class Imbalance","display_name":"Multimodal Deep Generative Model for Semi-Supervised Learning under Class Imbalance","publication_year":2026,"publication_date":"2026-05-07","ids":{"openalex":"https://openalex.org/W7160592995","doi":"https://doi.org/10.48550/arxiv.2605.06289"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.06289","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.06289","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.06289","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5126015040","display_name":"Heegeon Yoon","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yoon, Heegeon","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5135639734","display_name":"Heeyoung Kim","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kim, Heeyoung","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9524999856948853,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9524999856948853,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.004000000189989805,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11653","display_name":"Financial Distress and Bankruptcy Prediction","score":0.0034000000450760126,"subfield":{"id":"https://openalex.org/subfields/1402","display_name":"Accounting"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6111999750137329},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5590000152587891},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5425000190734863},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5134999752044678},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.5092999935150146},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.4018999934196472},{"id":"https://openalex.org/keywords/latent-variable","display_name":"Latent variable","score":0.400299996137619},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.3878999948501587},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.3871999979019165},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.3790999948978424}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7107999920845032},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7031999826431274},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.640500009059906},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6111999750137329},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5590000152587891},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5425000190734863},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5134999752044678},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5092999935150146},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.4018999934196472},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.400299996137619},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.3878999948501587},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3871999979019165},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.3790999948978424},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3508000075817108},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.3476000130176544},{"id":"https://openalex.org/C18653775","wikidata":"https://www.wikidata.org/wiki/Q1333358","display_name":"Joint probability distribution","level":2,"score":0.31839999556541443},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.31769999861717224},{"id":"https://openalex.org/C65965080","wikidata":"https://www.wikidata.org/wiki/Q1806885","display_name":"Latent variable model","level":3,"score":0.31349998712539673},{"id":"https://openalex.org/C2780440489","wikidata":"https://www.wikidata.org/wiki/Q5227278","display_name":"Data-driven","level":2,"score":0.3107999861240387},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.3059999942779541},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.3037000000476837},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.30169999599456787},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.2912999987602234},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.2897999882698059},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2833999991416931},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.27079999446868896},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.26829999685287476},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.2653000056743622},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.26510000228881836},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.25940001010894775}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.06289","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.06289","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.06289","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.06289","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"When":[0],"modeling":[1],"class-imbalanced":[2],"data,":[3,43,67],"it":[4,68],"is":[5,27,69],"crucial":[6],"to":[7,18,71],"address":[8,51,115],"the":[9,22,45,62,127,134,149],"imbalance,":[10,53,117],"as":[11],"models":[12,50],"trained":[13],"on":[14,40,152,163],"such":[15],"data":[16,36,157,185],"tend":[17],"be":[19],"biased":[20],"towards":[21],"majority":[23],"classes.":[24],"This":[25],"problem":[26],"amplified":[28],"under":[29,88],"partial":[30],"supervision,":[31],"where":[32],"pseudo-labels":[33],"for":[34,85,96,126,147,181],"unlabeled":[35,156],"are":[37],"predicted":[38],"based":[39],"imbalanced":[41,139,187],"labeled":[42,154,183],"propagating":[44],"bias.":[46],"While":[47],"recent":[48],"semi-supervised":[49,86],"class":[52,89,116,188],"they":[54],"typically":[55],"assume":[56],"single-modal":[57],"input":[58],"data.":[59,140],"However,":[60],"with":[61,109,123,186],"growing":[63],"availability":[64],"of":[65],"multimodal":[66,81,184],"essential":[70],"leverage":[72],"complementary":[73],"modalities.":[74],"In":[75],"this":[76],"article,":[77],"we":[78,118],"propose":[79],"a":[80,110,143],"deep":[82],"generative":[83],"model":[84,151,171],"learning":[87],"imbalance.":[90],"Our":[91],"approach":[92],"uses":[93],"separate":[94],"encoders":[95],"each":[97],"modality,":[98],"sharing":[99],"latent":[100,136],"variables":[101],"across":[102],"modalities,":[103],"and":[104,130,155,165],"simplifies":[105],"joint":[106],"posterior":[107],"computation":[108],"product-of-experts":[111],"method.":[112],"To":[113],"further":[114],"replace":[119],"typical":[120],"Gaussian":[121],"distributions":[122,137],"Student's":[124],"t-distributions":[125],"prior,":[128],"encoder,":[129],"decoder,":[131],"better":[132],"capturing":[133],"heavy-tailed":[135],"in":[138,175],"We":[141],"derive":[142],"new":[144],"objective":[145],"function":[146],"training":[148],"proposed":[150],"both":[153],"using":[158],"$\u03b3$-power":[159],"divergence.":[160],"Empirical":[161],"results":[162],"benchmark":[164],"real-world":[166],"datasets":[167],"demonstrate":[168],"that":[169],"our":[170],"outperforms":[172],"baseline":[173],"methods":[174],"generalization,":[176],"achieving":[177],"superior":[178],"classification":[179],"performance":[180],"partially":[182],"distributions.":[189]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-09T00:00:00"}